INDEX

Explanations

terms related to toxicity in a scientific context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

乍

-0.58

AGR

-0.52

hado

-0.51

Ucraina

-0.51

 جغرافيا

-0.51

bleshooting

-0.50

AddTagHelper

-0.50

cri

-0.49

{}{}

-0.49

ydd

-0.48

POSITIVE LOGITS

[toxicity=0]

1.21

Personendaten

0.70

ScopeManager

0.69

 HasFactory

0.69

 IndexPath

0.68

toxicity

0.66

}}/>

0.65

HomeAsUpEnabled

0.65

存于互联网档案馆

0.62

TargetException

0.61

Activations Density 0.060%

terms related to toxicity in a scientific context

No Comments

No Known Activations